Spiking Neural Network Based on Multi-Scale Saliency Fusion for Breast Cancer Detection

Abstract

Deep neural networks have been successfully applied in the field of image recognition and object detection, and the recognition results are close to or even superior to those from human beings. A deep neural network takes the activation function as the basic unit. It is inferior to the spiking neural network, which takes the spiking neuron model as the basic unit in the aspect of biological interpretability. The spiking neural network is considered as the third-generation artificial neural network, which is event-driven and has low power consumption. It modulates the process of nerve cells from receiving a stimulus to firing spikes. However, it is difficult to train spiking neural network directly due to the non-differentiable spiking neurons. In particular, it is impossible to train a spiking neural network using the back-propagation algorithm directly. Therefore, the application scenarios of spiking neural network are not as extensive as deep neural network, and a spiking neural network is mostly used in simple image classification tasks. This paper proposed a spiking neural network method for the field of object detection based on medical images using the method of converting a deep neural network to spiking neural network. The detection framework relies on the YOLO structure and uses the feature pyramid structure to obtain the multi-scale features of the image. By fusing the high resolution of low-level features and the strong semantic information of high-level features, the detection precision of the network is improved. The proposed method is applied to detect the location and classification of breast lesions with ultrasound and X-ray datasets, and the results are 90.67% and 92.81%, respectively.

A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018 to 2023)

“…Also, YOLO has shown tremendous success in the detection and classification of breast masses in mammograms [19], [79], [90]- [92]. Its use in such applications has proven to significantly reduce the time, cost, and potential for human error inherent in traditional methods of mammogram evaluation.…”

“…This data can be effectively analyzed using AI and machine learning tools like YOLO to extract valuable insights that can aid in diagnosis and treatment planning. For instance, YOLO has been used to detect and classify breast masses in mammograms [19], [79], [90]- [92]. The traditional evaluation process of screening mammograms is a laborious task, requiring significant time, cost, and human resources, and is prone to errors due to fatigue and the inherent subjectivity of human evaluation.…”

“…--INbreast was used in 4 papers [17], [90], [91], and [79]. --Digital Database for Screening Mammography (DDSM) was used in 2 papers [92] and [17].…”

STNet: A novel spiking neural network combining its own time signal with the spatial signal of an artificial neural network

“…The human brain disposes of information between neurons through electrical motivations (Taherkhani et al, 2020 ). Therefore, due to its discrete spiking signals and dynamics, an SNN is more biologically realistic and biologically interpretable than an ANN (Fu and Dong, 2022 ). Meanwhile, because of its discrete and efficient event-driven computing, an SNN consumes less energy than an ANN in the implementation of neuromorphic hardware (Kheradpisheh and Masquelier, 2020 ).…”